L05 Annotation & Positioning

Data Visualization (STAT 302)

Overview

The goal of this lab is to explore methods for annotating and positioning with ggplot2 plots. This lab also utilizes scale_* to a greater degree which is part of our next reading. In fact, students may find going through/reading chapter 11 Colour scales and legends useful.

Datasets

We’ll be using the blue_jays.rda, titanic.rda, Aus_athletes.rda, and tech_stocks.rda datasets.

Code

# Load package(s)
library(ggplot2)
library(ggrepel)
library(patchwork)
library(cowplot)
library(tidyverse)
# Load data
load("data/titanic.rda")
load("data/Aus_athletes.rda")
load("data/blue_jays.rda")
load("data/tech_stocks.rda")

Exercises

Complete the following exercises.

Exercise 1

Using the blue_jays.rda dataset, recreate the following graphic as precisely as possible.

Hints:

• Transparency is 0.8
• Point size 2
• Create a label_info dataset that is a subset of original data, just with the 2 birds to be labeled
• Shift label text horizontally by 0.5
• See ggplot2 textbook 8.3 building custom annotations
• Annotation size is 4
• Classic theme

Solution

Code

#Location info for annotate
y_range <- range(blue_jays$Head)
x_range <- range(blue_jays$Mass)
caption <- "Head length versus body mass for 123 blue jays"
# data for labels: geom_text()
label_info <- blue_jays |> 
  filter(BirdID %in%
           c("1142-05914", "702-90567"))
#build plot
ggplot(blue_jays,
       aes(x = Mass,
           y = Head,
           color = KnownSex)) +
geom_point(
  size = 2,
  alpha = 0.8,
  show.legend = FALSE
  ) +
  geom_text(
    data = label_info,
    mapping = aes(label = KnownSex),
    show.legend = FALSE,
    nudge_x = 0.5) +
  theme_classic() +
  labs(
    x = "Body mass (g)",
    y = "Head length (mm)"
    ) +
  annotate(
    geom = "text", 
    x = x_range[1],#1st value of the coordinate
    y = y_range[2], #2nd value of the coordinate
    label = caption,
    hjust = 0,
    vjust = 1)

Exercise 2

Using the tech_stocks dataset, recreate the following graphics as precisely as possible. Use the column price_indexed.

Plot 1

Hints:

• Create a label_info dataset that is a subset of original data, just containing the last day’s information for each of the 4 stocks
• serif font
• Annotation size is 4

Solution

Code

y_rangee2p1 <- range(tech_stocks$price_indexed)
x_rangee2p1 <- range(tech_stocks$date)
captione2p1 <- "Stock price over time for four major tech companies"

label_infoe2p1  <- tech_stocks |> 
  filter(date %in%
           c("2017-06-02"))


ggplot(tech_stocks, aes(x = date, y = price_indexed, color = company)) +
  geom_line(show.legend = FALSE) + 
  geom_text(
    data = label_infoe2p1,
    mapping = aes(label = company),
    color = "black",
    family = "serif") +
  annotate(
    geom = "text", 
    x = x_rangee2p1[1],#1st value of the coordinate
    y = y_rangee2p1[2], #2nd value of the coordinate
    label = captione2p1,
    hjust = 0,
    vjust = 1,
    family = "serif",
    size = 4,
    show.legend = FALSE) +
  labs(
    x = "Date",
    y = "Stock price, indexed") +
  theme_minimal()

Plot 2

Hints:

• Package ggrepel
  • box.padding is 0.6
  • Minimum segment length is 0
  • Horizontal justification is to the right
  • seed of 9876
• Annotation size is 4
• serif font

Solution

Code

y_rangee2p1 <- range(tech_stocks$price_indexed)
x_rangee2p1 <- range(tech_stocks$date)
captione2p1 <- "Stock price over time for four major tech companies"

label_infoe2p1  <- tech_stocks |> 
  filter(date %in%
           c("2017-06-02"))


ggplot(tech_stocks, aes(x = date, y = price_indexed, color = company)) +
  geom_line(show.legend = FALSE) + 
  geom_text_repel(
    data = label_infoe2p1,
    mapping = aes(label = company),
    box.padding = 0.6,
    min.segment.length = 0,
    seed = 9876,
    show.legend = FALSE,
    hjust = 1,
    color = "black",
    family = "serif") +
  annotate(
    geom = "text", 
    x = x_rangee2p1[1],#1st value of the coordinate
    y = y_rangee2p1[2], #2nd value of the coordinate
    label = captione2p1,
    hjust = 0,
    vjust = 1,
    family = "serif",
    size = 4,
    show.legend = FALSE) +
  labs(
    x = "Date",
    y = "Stock price, indexed") +
  theme_minimal()

Exercise 3

Using the titanic.rda dataset, recreate the following graphic as precisely as possible.

Hints:

• Create a new variable that uses died and survived as levels/categories
• Hex colors: #D55E00D0, #0072B2D0 (no alpha is being used)

Solution

Code

# Create the new survival_status variable
titanic <- titanic %>%
  mutate(survival_status = factor(ifelse(survived == 1, "survived", "died"), levels = c("died", "survived")))

# Create the plot
ggplot(titanic, aes(x = sex, fill = sex)) +
  geom_bar(position = "dodge") +
  facet_grid(survival_status ~ class) +
  scale_fill_manual(values = c("female" = "#D55E00D0", "male" = "#0072B2D0")) +
  labs(y = "count") +
  theme_minimal() +
  theme(legend.position = "none")

Exercise 4

Use the athletes_dat dataset — extracted from Aus_althetes.rda — to recreate the following graphic as precisely as possible. Create the graphic twice: once using patchwork and once using cowplot.

Code

# Get list of sports played by BOTH sexes
both_sports <- Aus_athletes |>
  # dataset of columns sex and sport 
  # only unique observations
  distinct(sex, sport) |>
  # see if sport is played by one gender or both
  count(sport) |>
  # only want sports played by BOTH sexes
  filter(n == 2) |>
  # get list of sports
  pull(sport)

# Process data
athletes_dat <- Aus_athletes |>
  # only keep sports played by BOTH sexes
  filter(sport %in% both_sports) |>
  # rename track (400m) and track (sprint) to be track
  # case_when will be very useful with shiny apps
  mutate(
    sport = case_when(
      sport == "track (400m)" ~ "track",
      sport == "track (sprint)" ~ "track",
      TRUE ~ sport
      )
    )

Hints:

• Build each plot separately
• Bar plot: lower limit 0, upper limit 95
• Bar plot: shift bar labels by 5 units and top justify
• Bar plot: label size is 5
• Bar plot: #D55E00D0 & #0072B2D0 — no alpha
• Scatterplot: #D55E00D0 & #0072B2D0 — no alpha
• Scatterplot: filled circle with “white” outline; size is 3
• Scatterplot: rcc is red blood cell count; wcc is white blood cell count
• Boxplot: outline #D55E00 and #0072B2; shading #D55E0040 and #0072B240
• Boxplot: should be made narrower; 0.5
• Boxplot: Legend is in top-right corner of bottom plot
• Boxplot: Space out labels c("female ", "male")
• Boxplot: Legend shading matches hex values for top two plots

Using patchwork

Solution

Code

#label info(bar plot)
label_info <- athletes_dat |>  count(sex)

#bar graph 
plot_1_bar_plot <- ggplot(data = athletes_dat, mapping = aes(sex, fill = sex)) +
  geom_bar() + 
  geom_text(
    data = label_info,
    mapping = aes(y = n, label = n),
    size = 5,
    vjust = 1,
    nudge_y = -5
  ) +
  scale_fill_manual(
    values = c("#D55E00D0","#0072B2D0"),
    guide = "none"
    ) +
  scale_x_discrete(name = NULL, labels = c("female", "male")) + 
  scale_y_continuous(name = "number",
                     limits = c(0,95), 
                     expand = c(0,0)
                     ) +
  theme_minimal()

#scatterplot

plot_2_scatter <- ggplot(athletes_dat, aes(rcc, wcc, fill = sex)) +
  geom_point(
    shape = 21, 
    color = "white",
    size = 3) + 
  scale_fill_manual(
    values = c("#D55E00D0","#0072B2D0"),
    guide = "none"
    ) +
  theme_minimal() +
  labs( 
    x = "RBC count", 
    y = "WBC count")


#boxplots 
plot_3_boxplot <- ggplot(
  athletes_dat,
  aes(sport, pcBfat, fill = sex, color = sex)
  ) +
  geom_boxplot(width = 0.5) +
  scale_color_manual(
    values = c("#D55E00D0","#0072B2D0"),
    guide = "none"
    ) + 
  scale_fill_manual(
    name = NULL,
    values = c("#D55E0040","#0072B240"),
    labels = c("female    ", "male")
    ) +
  theme_minimal() +
  theme(
    legend.justification = c(1,1),
    legend.position = c(1,1),
    legend.direction = "horizontal"
  ) +
  labs( 
    x = NULL, 
    y = "% body fat"
    ) +
  guides(
    fill = guide_legend(
      override.aes = list(
        color = NA,
        fill = c("#D55E00D0","#0072B2D0")
        )
      )
    )

#  building graphic with patchwork
(plot_1_bar_plot + plot_2_scatter) / plot_3_boxplot

Using cowplot

Use cowplot::plot_grid() to combine them.

Solution

Code

#  building graphic with cowplot
top_row <- plot_grid(plot_1_bar_plot, plot_2_scatter, align = "h")
plot_grid(top_row, plot_3_boxplot, ncol = 1)

Exercise 5

Create the following graphic using patchwork.

Hints:

• Use plots created in Exercise 4
• inset theme is classic
  • Useful values: 0, 0.45, 0.75, 1
• plot annotation "A"

Solution

Code

#bar graph 
plot_12_bar_plot <- ggplot(data = athletes_dat, mapping = aes(sex, fill = sex)) +
  geom_bar() + 
  geom_text(
    data = label_info,
    mapping = aes(y = n, label = n),
    size = 5,
    vjust = 1,
    nudge_y = -5
  ) +
  scale_fill_manual(
    values = c("#D55E00D0","#0072B2D0"),
    guide = "none"
    ) +
  scale_x_discrete(name = NULL, labels = c("female", "male")) + 
  scale_y_continuous(name = "number",
                     limits = c(0,95), 
                     expand = c(0,0)
                     ) +
  theme_classic()
combined_plot <- plot_2_scatter +
  inset_element(plot_12_bar_plot, 0.75, 0, 1, .45) + plot_annotation(tag_levels = 'A')

combined_plot